Table 5.

Classification performance metrics of the proposed method.

		Specificity (%)	Precision (%)	Recall (%)	F1 Score (%)	AUC	MCC
Phase-1	Cosine KNN	95.35	90.09	85.93	87.96	0.9064	0.8230
	Linear Discriminant	94.70	89.06	87.69	88.37	0.9120	0.8272
	Bagged Trees Ensemble	97.19	94.06	90.55	92.27	0.9387	0.8861
	SqueezeNet Deep Learning	99.67	99.25	88.13	93.36	0.9390	0.9072
	Medium Gaussian SVM	98.16	96.22	95.16	95.69	0.9666	0.9359
	Majority Voting-1	99.98	99.83	99.07	99.51	0.9974	0.9855
Phase-2	Logistic Regression	88.12	87.94	86.79	87.36	0.8746	0.7492
	Linear Discriminant	91.14	90.82	87.88	89.33	0.8951	0.7907
	Bagged Trees Ensemble	91.57	91.39	89.61	90.49	0.9059	0.8120
	Cosine KNN	97.19	96.83	86.14	91.18	0.9167	0.8386
	Medium Gaussian SVM	96.33	96.08	90.26	93.08	0.9329	0.8675
	Majority Voting-2	99.73	99.69	98.63	99.23	0.9928	0.9518
	Overall Majority Voting	99.88	99.78	98.90	99.40	0.9956	0.9720